iPADD
Diabetes Mellitus is a chronic metabolic disease, which causes the imbalance in blood glucose homeostasis and further lead to severe complications.
With the increasing population of diabetes, there is an urgent need to develop drugs to treat diabetes.
The development of artificial intelligence provides a powerful tool for accelerating the discovery of antidiabetic drug.
This work aims to establish a predictor called iPADD for discovering potential antidiabetic drugs.
In the predictor, we used four kinds of molecular fingerprints and their combinations to encode the drugs, and then adopted minimum-Redundancy-Maximum-Relevance(mRMR) combined with incremental feature selection (IFS) strategy to screen optimal features.
Based on the optimal feature subset, eight machine-learning algorithms were applied to train models by using 5-fold cross-validation.
The best model could produce an accuracy (ACC) of 0.983 with the area under the receiver operating characteristic curve (auROC) value of 0.989 on independent test set.
We hope that the model can provide strong support for the screening of diabetes drugs.